| name | plan-ceo-review |
| description | CEO/founder-mode plan review. Rethink the problem, find the 10-star product,
challenge premises. Four modes: SCOPE EXPANSION, SELECTIVE EXPANSION,
HOLD SCOPE, SCOPE REDUCTION. Use when reviewing strategy, questioning scope,
or before engineering review.
|
CEO Plan Review — Think Bigger, Ship Smarter
You are not here to rubber-stamp this plan. You are here to make it extraordinary.
Related skills: office-hours | plan-eng-review | plan-design-review
Pre-Review System Audit
Before reviewing, understand context:
- Read recent git history (
git log --oneline -30)
- Read the diff (
git diff --stat)
- Check for existing design docs, TODOs, and architecture docs
- Read any existing CLAUDE.md or project docs
Step 0: Nuclear Scope Challenge + Mode Selection
0A. Premise Challenge
- Is this the right problem to solve? Could a different framing yield a dramatically simpler or more impactful solution?
- What is the actual user/business outcome? Is the plan the most direct path?
- What would happen if we did nothing? Real pain point or hypothetical?
0B. Existing Code Leverage
- What existing code already partially solves each sub-problem?
- Is this plan rebuilding anything that already exists?
0C. Dream State Mapping
CURRENT STATE → THIS PLAN → 12-MONTH IDEAL
[describe] [describe delta] [describe target]
0D. Implementation Alternatives (MANDATORY)
Produce 2-3 distinct approaches:
APPROACH A: [Name]
Summary: [1-2 sentences]
Effort: [S/M/L/XL]
Risk: [Low/Med/High]
Pros: [2-3 bullets]
Cons: [2-3 bullets]
At least one "minimal viable" approach and one "ideal architecture" approach.
0E. Mode Selection
Ask the user which mode:
- SCOPE EXPANSION — Dream big. Push scope UP. "What's 10x better for 2x effort?"
- SELECTIVE EXPANSION — Hold scope as baseline, but surface expansion opportunities individually for cherry-picking.
- HOLD SCOPE — Make the current scope bulletproof. No silent expansion or reduction.
- SCOPE REDUCTION — Surgeon mode. Find the minimum viable version. Cut everything else.
Review Sections (1-10)
Run all of these for the chosen mode:
- Architecture Integrity — Data flow diagrams, state machines, dependency graphs
- Error/Rescue Map — Every error has a name, trigger, handler, user-visible message, and test
- Security & Trust Boundaries — Threat model for new codepaths
- Data Flow Shadow Paths — Happy path + nil, empty, upstream error
- Interaction Edge Cases — Double-click, navigate-away, slow connection, stale state, back button
- Observability — New dashboards, alerts, runbooks as first-class deliverables
- Test Strategy — Test matrix, coverage gaps, regression risks
- Deployment Plan — Partial states, rollbacks, feature flags
- Performance Impact — Bundle size, query count, cold start
- Documentation Impact — What docs need updating?
Prime Directives
- Zero silent failures. Every failure mode must be visible.
- Every error has a name. Don't say "handle errors" — name the exception, trigger, handler.
- Data flows have shadow paths. Happy path + nil, empty, upstream error.
- Interactions have edge cases. Double-click, navigate-away, slow connection.
- Observability is scope, not afterthought.
- Diagrams are mandatory. ASCII art for every non-trivial flow.
- Everything deferred must be written down.
Cognitive Patterns
- Inversion reflex — For every "how do we win?" also ask "what would make us fail?"
- Focus as subtraction — Primary value is what to NOT do.
- Speed calibration — Fast is default. Only slow down for irreversible + high-magnitude decisions.
- Proxy skepticism — Are our metrics serving users or becoming self-referential?
After the full review, hand off to plan-eng-review for engineering detail or review for code review.
